scrapy 模拟登陆

最新推荐文章于 2024-08-22 16:33:52 发布

转载最新推荐文章于 2024-08-22 16:33:52 发布 · 53 阅读

0 ·

CC 4.0 BY-SA版权

原文链接：http://www.cnblogs.com/Erick-L/p/6841417.html

文章标签：

#python

import scrapy
import urllib.request
from scrapy.http import Request,FormRequest

class LoginspdSpider(scrapy.Spider):
    name = "loginspd"
    allowed_domains = ["douban.com"]
    start_urls = ['http://douban.com/']
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/50.0.2661.102 Safari/537.36 QIHU 360EE'}
    def start_requests(self):
        return [Request('https://www.douban.com/accounts/login',meta={'cookiejar':1},callback=self.parse)]
    def parse(self, response):
        # 获取验证码地址
        captcha = response.xpath('//img[@id="captcha_image"]/@src').extract()
        if len(captcha)>0:
            print('有验证码')
            localpath = 'D:/Captcha.png'
            urllib.request.urlretrieve(captcha[0],filename=localpath)
            print('请查看本地验证码并输入:')
            captcha_value = input()
            data = {
                'form_email':'83*****81@qq.com',
                'form_password':'*****1',
                'captcha-solution':captcha_value,
                'redir':'https://www.douban.com/people/161282530/',
            }
        else:
            print('没有验证码')
            data = {
                'form_email': '834****81@qq.com',
                'form_password': '*****',
                'redir': 'https://www.douban.com/people/161282530/',
            }
        print('登录中。。。。')

        return [FormRequest.from_response(response,
                                          # meta = {'cookiejar':response.meta['cookiejar']}
                                          headers =self.headers,
                                          formdata=data,
                                          callback = self.next,)]
    def next(self,response):
        print('此时已经登录完成并爬取个人中心数据')
        title = response.xpath('/html/head/title/text()').extract()
        print(title)